VietDunghacker
VietDunghacker
Thank you.
@Jintao-Huang vllm is great, but unfortunately vllm does not support all models in this repo. For instance, Phi-3 Vision is supported in their Github repo but not in the official...
Qwen2-VL seems to not compatible with FlashAttention? When I add "--use_flash_attn True", I encountered this error (CUDA_LAUNCH_BLOCKING was enabled to print the exact trace): [rank0]: File "***/lib/python3.10/site-packages/transformers/models/qwen2_vl/modeling_qwen2_vl.py", line 182, in...
It did work, thanks.
When I fine-tune Qwen3-VL with the latest ms-swift framework and transformers==4.57.0, if I turn on liger kernel, the training process will be frozen indefinitely. Can you check it?